Uncertainty-Aware Model Adaptation for Unsupervised Cross-Domain Object Detection

Abstract

This work tackles the unsupervised cross-domain object detection problem which aims to generalize a pre-trained object detector to a new target domain without labels. We propose an uncertainty-aware model adaptation method, which is based on two motivations: 1) the estimation and exploitation of model uncertainty in a new domain is critical for reliable domain adaptation; and 2) the joint alignment of distributions for inputs (feature alignment) and outputs (self-training) is needed. To this end, we compose a Bayesian CNN-based framework for uncertainty estimation in object detection, and propose an algorithm for generation of uncertainty-aware pseudo-labels. We also devise a scheme for joint feature alignment and self-training of the object detection model with uncertainty-aware pseudo-labels. Experiments on multiple cross-domain object detection benchmarks show that our proposed method achieves state-of-the-art performance.

11 pages, 4 figures

References in corpus (5)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Learning Transferable Features with Deep Adaptation Networks
• Deep Domain Confusion: Maximizing for Domain Invariance
• Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks
• Uncertainty-aware Self-training for Text Classification with Few Labels